no code implementations • 28 Dec 2024 • Qianli Liao, Liu Ziyin, Yulu Gan, Brian Cheung, Mark Harnett, Tomaso Poggio
Over the last four decades, the amazing success of deep learning has been driven by the use of Stochastic Gradient Descent (SGD) as the main optimization technique.
no code implementations • 27 Sep 2024 • Yulu Gan, Tomer Galanti, Tomaso Poggio, Eran Malach
This research reveals the unique computational abilities of ARDTs, aiming to broaden the architectural diversity in language model development.
1 code implementation • 24 Aug 2024 • Gaole Dai, Chun-Kai Fan, Yiming Tang, Zhi Zhang, Yuan Zhang, Yulu Gan, Qizhe Zhang, Cheng-Ching Tseng, Shanghang Zhang, Tiejun Huang
Advances in Parameter-Efficient Fine-Tuning (PEFT) bridged the performance gap with Full Fine-Tuning (FFT) through sophisticated analysis of pre-trained parameter spaces.
no code implementations • 14 Dec 2023 • Anthony Chen, Huanrui Yang, Yulu Gan, Denis A Gudovskiy, Zhen Dong, Haofan Wang, Tomoyuki Okuno, Yohei Nakata, Kurt Keutzer, Shanghang Zhang
In particular, we build a tree-like Split-Ensemble architecture by performing iterative splitting and pruning from a shared backbone model, where each branch serves as a submodel corresponding to a subtask.
no code implementations • 24 Nov 2023 • Cuifeng Shen, Yulu Gan, Chen Chen, Xiongwei Zhu, Lele Cheng, Tingting Gao, Jinzhi Wang
The goal of conditional image-to-video (cI2V) generation is to create a believable new video by beginning with the condition, i. e., one image and text. The previous cI2V generation methods conventionally perform in RGB pixel space, with limitations in modeling motion consistency and visual continuity.
no code implementations • 31 Oct 2023 • Peixiang Huang, Songtao Zhang, Yulu Gan, Rui Xu, Rongqi Zhu, Wenkang Qin, Limei Guo, Shan Jiang, Lin Luo
Deep learning in digital pathology brings intelligence and automation as substantial enhancements to pathological analysis, the gold standard of clinical diagnosis.
1 code implementation • 30 Sep 2023 • Yulu Gan, Sungwoo Park, Alexander Schubert, Anthony Philippakis, Ahmed M. Alaa
We then use a large language model to paraphrase prompt templates that convey the specific tasks to be conducted on each image, and through this process, we create a multi-modal and multi-task training dataset comprising input and output images along with annotated instructions.
no code implementations • 21 Jun 2023 • Mingjie Pan, Yulu Gan, Fangxu Zhou, Jiaming Liu, Aimin Wang, Shanghang Zhang, Dawei Li
Since the diffusion model learns the universal structural distribution of biological tissues, which is independent of the axial resolution, DiffuseIR can reconstruct authentic images with unseen low-axial resolutions into a high-axial resolution without requiring re-training.
no code implementations • 16 Apr 2023 • Jiaxin Ge, Hongyin Luo, Siyuan Qian, Yulu Gan, Jie Fu, Shanghang Zhang
Chain of Thought is a simple and effective approximation to human reasoning process and has been proven useful for natural language processing (NLP) tasks.
1 code implementation • 17 Mar 2023 • Senqiao Yang, Jiarui Wu, Jiaming Liu, Xiaoqi Li, Qizhe Zhang, Mingjie Pan, Yulu Gan, Zehui Chen, Shanghang Zhang
The visual prompts have provided an efficient manner in addressing visual cross-domain problems.
no code implementations • 8 Dec 2022 • Yulu Gan, Yan Bai, Yihang Lou, Xianzheng Ma, Renrui Zhang, Nian Shi, Lin Luo
Since pseudo labels are noisy and unreliable, these methods suffer from catastrophic forgetting and error accumulation when dealing with dynamic data distributions.
no code implementations • CVPR 2023 • Yulu Gan, Mingjie Pan, Rongyu Zhang, Zijian Ling, Lingran Zhao, Jiaming Liu, Shanghang Zhang
To enable the device model to deal with changing environments, we propose a new learning paradigm of Cloud-Device Collaborative Continual Adaptation, which encourages collaboration between cloud and device and improves the generalization of the device model.